A CUDA approach to compute perishable inventory control policies using value iteration.
Gloria Ortega LópezEligius M. T. HendrixInmaculada GarcíaPublished in: J. Supercomput. (2019)
Keyphrases
- control policies
- optimal policy
- markov decision processes
- action space
- state space
- stochastic optimization problems
- finite horizon
- reinforcement learning
- infinite horizon
- control strategies
- control policy
- dynamic programming
- control system
- motion control
- decision problems
- markov decision process
- real time
- finite state
- long run
- multistage
- mobile robot
- decision making